Development of a PET/CT molecular radiomics-clinical model to predict thoracic lymph node metastasis of invasive lung adenocarcinoma ≤ 3 cm in diameter.

BACKGROUND: To investigate the value of 18F-FDG PET/CT molecular radiomics combined with a clinical model in predicting thoracic lymph node metastasis (LNM) in invasive lung adenocarcinoma (≤ 3 cm). METHODS: A total of 528 lung adenocarcinoma patients were enrolled in this retrospective study. Five models were developed for the prediction of thoracic LNM, including PET radiomics, CT radiomics, PET/CT radiomics, clinical and integrated PET/CT radiomics-clinical models. Ten PET/CT radiomics features and two clinical characteristics were selected for the construction of the integrated PET/CT radiomics-clinical model. The predictive performance of all models was examined by receiver operating characteristic (ROC) curve analysis, and clinical utility was validated by nomogram analysis and decision curve analysis (DCA). RESULTS: According to ROC curve analysis, the integrated PET/CT molecular radiomics-clinical model outperformed the clinical model and the three other radiomics models, and the area under the curve (AUC) values of the integrated model were 0.95 (95% CI: 0.93-0.97) in the training group and 0.94 (95% CI: 0.89-0.97) in the test group. The nomogram analysis and DCA confirmed the clinical application value of this integrated model in predicting thoracic LNM. CONCLUSIONS: The integrated PET/CT molecular radiomics-clinical model proposed in this study can ensure a higher level of accuracy in predicting the thoracic LNM of clinical invasive lung adenocarcinoma (≤ 3 cm) compared with the radiomics model or clinical model alone.

A Machine Learning Model Based on PET/CT Radiomics and Clinical Characteristics Predicts ALK Rearrangement Status in Lung Adenocarcinoma.

OBJECTIVES: Anaplastic lymphoma kinase (ALK) rearrangement status examination has been widely used in clinic for non-small cell lung cancer (NSCLC) patients in order to find patients that can be treated with targeted ALK inhibitors. This study intended to non-invasively predict the ALK rearrangement status in lung adenocarcinomas by developing a machine learning model that combines PET/CT radiomic features and clinical characteristics. METHODS: Five hundred twenty-six patients of lung adenocarcinoma with PET/CT scan examination were enrolled, including 109 positive and 417 negative patients for ALK rearrangements from February 2016 to March 2019. The Artificial Intelligence Kit software was used to extract radiomic features of PET/CT images. The maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) logistic regression were further employed to select the most distinguishable radiomic features to construct predictive models. The mRMR is a feature selection method, which selects the features with high correlation to the pathological results (maximum correlation), meanwhile retain the features with minimum correlation between them (minimum redundancy). LASSO is a statistical formula whose main purpose is the feature selection and regularization of data model. LASSO method regularizes model parameters by shrinking the regression coefficients, reducing some of them to zero. The feature selection phase occurs after the shrinkage, where every non-zero value is selected to be used in the model. Receiver operating characteristic (ROC) analysis was used to evaluate the performance of the models, and the performance of different models was compared by the DeLong test. RESULTS: A total of 22 radiomic features were extracted from PET/CT images for constructing the PET/CT radiomic model, and majority of these features used were based on CT features (20 out of 22), only 2 PET features were included (PET percentile 10 and PET difference entropy). Moreover, three clinical features associated with ALK mutation (age, burr and pleural effusion) were also employed to construct a combined model of PET/CT and clinical model. We found that this combined model PET/CT-clinical model has a significant advantage to predict the ALK mutation status in the training group (AUC = 0.87) and the testing group (AUC = 0.88) compared with the clinical model alone in the training group (AUC = 0.76) and the testing group (AUC = 0.74) respectively. However, there is no significant difference between the combined model and PET/CT radiomic model. CONCLUSIONS: This study demonstrated that PET/CT radiomics-based machine learning model has potential to be used as a non-invasive diagnostic method to help diagnose ALK mutation status for lung adenocarcinoma patients in the clinic.

Biodistribution characteristics and SPECT imaging of (99m)Tc-RET and (99m)Tc-REG in human lung cancer xenografts.

OBJECTIVE: To investigate the biodistribution and single-photon emission computed tomography (SPECT) imaging of (99m)Tc-labeled arginine-glutamic acid-threonine (RET) and arginine-glutamic acid-glycine (REG) in nude mice bearing human lung cancer xenografts. MATERIALS AND METHODS: RET and REG were labeled directly with (99m)Tc and their binding efficiency to tumor cells was measured in human nonsmall cell lung cancer H1299 cells. After intravenously injecting (99m)Tc-RET and (99m)Tc-REG into normal mice and nude mice bearing human lung cancer xenografts, their biodistribution was measured at different postinjection times, and percentages of injected dose per gram tissue (% ID/g) of organs of interest were calculated. The mice bearing H1299 lung cancer xenografts were scanned by SPECT at different times following the (99m)Tc-RET or (99m)Tc-REG injection. RESULTS: The radiochemical purity of (99m)Tc-RET and (99m)Tc-REG was 93.15%±2.02% and 92.90%±2.86%, respectively. The binding rate of (99m)Tc-RET and (99m)Tc-REG to H1299 cells was 3.56%±0.37% and 2.32%±0.31%, respectively. The uptake of (99m)Tc-RET and (99m)Tc-REG in tumor was 4.96±1.05% ID/g at 4 hours postinjection and 1.95±0.73% ID/g at 2 hours postinjection, respectively. Tumors in nude mice could be best imaged at 4.5-6 hours postinjection of (99m)Tc-RET. CONCLUSION: (99m)Tc-RET has a higher binding rate to H1299 cells than (99m)Tc-REG and might be used as a potential lung cancer imaging agent.

Tissue-targeting lead generation and optimization from random and directed screening of technetium-99m labeled tripeptide complex libraries in vivo.

BACKGROUND: Screening libraries against a molecular target in vitro are idealized models that cannot reflect the real state in vivo where biomolecules coexist and interact. C-terminal amide tripeptides labelled with Technetium-99m can provide a unique noninvasive approach to trace a large number of compounds in vivo. METHODS: The C-terminal amide tripeptide libraries were synthesized on Rink Amide-MBHA resin using iterative and pooling protocol. Technetium (V) oxo core [TcO(3+)] was bound to each tripeptide via 4 deprotonated nitrogen atoms to form a library of 8000 (99m)Tc tripeptoid complexes. The radiocombinatorial screening (RCS) in vivo was carried out on SD rats and A549 tumour bearing mice. RESULTS: Signals of tissue distribution and metabolism of libraries were recorded by counting or imaging and tissue targeting leads identified by both random and directed RCS. Among them, (99m)Tc RPA, (99m)Tc VIG and (99m)Tc RES had specific tissue targeting in kidney, liver and tumour respectively. The percent injected dose per gram tissue of (99m)Tc labelled leads in their target tissue was highly structure dependent. Because the nontarget tissue binding and the metabolism of (99m)Tc tripeptoid sublibraries were simultaneously monitored successfully by RCS, the interference of background activity was limited to the lowest level. Optimization of renal function agent from the labelled libraries was carried out by directed screening. (99m)Tc DSG was finally identified the most promising agent for renal function studies. CONCLUSIONS: RCS in vivo is a powerful tool for the discovery of tissue targeting drugs. The potential screening bias is probably the major limitation of labelled libraries.